© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111098
    Prev
    Next
    INDEX
    Explanations

    alphabetical order, parties, courts

    np_acts-logits-general · gemini-2.5-flash-lite

    column, studies, numbers, riots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     봤
    0.48
     interstit
    0.47
     wisely
    0.47
     sensibly
    0.46
    πων
    0.46
     resusc
    0.46
     mentored
    0.45
     पॉलिटी
    0.44
     mêmes
    0.44
     समझेंगे
    0.43
    POSITIVE LOGITS
    ]='
    0.46
     অভিযান
    0.45
     丶
    0.44
     Kampung
    0.43
    වල
    0.43
    Duong
    0.43
     、,
    0.43
     ദു
    0.43
     HOTEL
    0.42
     Gemeinde
    0.41
    Activations Density 0.001%

    No Known Activations